Running a One-Way or Two-Way/Factorial ANOVA
Avery Cumming
2024-12-05
1 Loading Libraries
#install.packages("afex")
#install.packages("emmeans")
#install.packages("ggbeeswarm")
library(psych) # for the describe() command
library(ggplot2) # to visualize our results##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphalibrary(expss) # for the cross_cases() command## Loading required package: maditr##
## To modify variables or add new variables:
## let(mtcars, new_var = 42, new_var2 = new_var*hp) %>% head()##
## Attaching package: 'maditr'## The following object is masked from 'package:base':
##
## sort_by##
## Attaching package: 'expss'## The following object is masked from 'package:ggplot2':
##
## varslibrary(car) # for the leveneTest() command## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:expss':
##
## recode## The following object is masked from 'package:psych':
##
## logitlibrary(afex) # to run the ANOVA ## Loading required package: lme4## Loading required package: Matrix##
## Attaching package: 'lme4'## The following object is masked from 'package:expss':
##
## dummy## ************
## Welcome to afex. For support visit: http://afex.singmann.science/## - Functions for ANOVAs: aov_car(), aov_ez(), and aov_4()
## - Methods for calculating p-values with mixed(): 'S', 'KR', 'LRT', and 'PB'
## - 'afex_aov' and 'mixed' objects can be passed to emmeans() for follow-up tests
## - Get and set global package options with: afex_options()
## - Set sum-to-zero contrasts globally: set_sum_contrasts()
## - For example analyses see: browseVignettes("afex")
## ************##
## Attaching package: 'afex'## The following object is masked from 'package:lme4':
##
## lmerlibrary(ggbeeswarm) # to run plot results
library(emmeans) # for posthoc tests## Welcome to emmeans.
## Caution: You lose important information if you filter this package's results.
## See '? untidy'2 Importing Data
# For HW, import the project dataset you cleaned previously this will be the dataset you'll use throughout the rest of the semester
d <- read.csv(file="Data/projectdata.csv", header=T)
# new code! this adds a column with a number for each row. It will make it easier if we need to drop outliers later
d$row_id <- 1:nrow(d)3 State Your Hypothesis
Note: For your HW, you will choose to run EITHER a one-way ANOVA (a single IV with more than 2 levels) OR a two-way/factorial ANOVA (at least two IVs). You will need to specify your hypothesis and customize your code based on the choice you make. We will run both versions of the test in the lab for illustrative purposes.
One-Way: We predict that there will be a significant effect of age on people’s narcissistic personality inventory.
4 Check Your Variables
# you only need to check the variables you're using in the current analysis
# even if you checked them previously, it's always a good idea to look them over again and be sure that everything is correct
str(d)## 'data.frame': 2132 obs. of 8 variables:
## $ ResponseId : chr "R_BJN3bQqi1zUMid3" "R_2TGbiBXmAtxywsD" "R_12G7bIqN2wB2N65" "R_39pldNoon8CePfP" ...
## $ age : chr "1 between 18 and 25" "1 between 18 and 25" "1 between 18 and 25" "1 between 18 and 25" ...
## $ gender : chr "f" "m" "m" "f" ...
## $ moa_maturity: num 3.67 3.33 3.67 3 3.67 ...
## $ belong : num 2.8 4.2 3.6 4 3.4 4.2 3.9 3.6 2.9 2.5 ...
## $ efficacy : num 3.4 3.4 2.2 2.8 3 2.4 2.3 3 3 3.7 ...
## $ npi : num 0.6923 0.1538 0.0769 0.0769 0.7692 ...
## $ row_id : int 1 2 3 4 5 6 7 8 9 10 ...# make our categorical variables of interest factors
# because we'll use our newly created row ID variable for this analysis, so make sure it's coded as a factor, too.
#d$CATVARIABLE <- as.factor(d$CATVARIABLE)
d$age <- as.factor(d$age)
d$row_id <- as.factor(d$row_id)
# we're going to recode our race variable into two groups: poc and white
# in doing so, we are creating a new variable "poc" that has 2 levels
table(d$age)##
## 1 between 18 and 25 2 between 26 and 35 3 between 36 and 45 4 over 45
## 1964 114 37 17d$over36[d$age == "1 between 18 and 25"] <- "1 between 18 and 25"
d$over36[d$age == "2 between 26 and 35"] <- "2 between 26 and 35"
d$over36[d$age == "3 between 36 and 45"] <- "over 36"
d$over36[d$age == "4 over 45"] <- "over 36"
table(d$over36)##
## 1 between 18 and 25 2 between 26 and 35 over 36
## 1964 114 54d$over36 <- as.factor(d$over36)
# check that all our categorical variables of interest are now factors
str(d)## 'data.frame': 2132 obs. of 9 variables:
## $ ResponseId : chr "R_BJN3bQqi1zUMid3" "R_2TGbiBXmAtxywsD" "R_12G7bIqN2wB2N65" "R_39pldNoon8CePfP" ...
## $ age : Factor w/ 4 levels "1 between 18 and 25",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ gender : chr "f" "m" "m" "f" ...
## $ moa_maturity: num 3.67 3.33 3.67 3 3.67 ...
## $ belong : num 2.8 4.2 3.6 4 3.4 4.2 3.9 3.6 2.9 2.5 ...
## $ efficacy : num 3.4 3.4 2.2 2.8 3 2.4 2.3 3 3 3.7 ...
## $ npi : num 0.6923 0.1538 0.0769 0.0769 0.7692 ...
## $ row_id : Factor w/ 2132 levels "1","2","3","4",..: 1 2 3 4 5 6 7 8 9 10 ...
## $ over36 : Factor w/ 3 levels "1 between 18 and 25",..: 1 1 1 1 1 1 1 1 1 1 ...# check our DV skew and kurtosis
describe(d$npi)## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 2132 0.27 0.3 0.15 0.23 0.23 0 1 1 1 -0.56 0.01# we'll use the describeBy() command to view our DV's skew and kurtosis across our IVs' levels
describeBy(d$npi, group = d$over36)##
## Descriptive statistics by group
## group: 1 between 18 and 25
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 1964 0.27 0.31 0.15 0.23 0.23 0 1 1 0.97 -0.63 0.01
## ------------------------------------------------------------
## group: 2 between 26 and 35
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 114 0.24 0.27 0.15 0.19 0.11 0 1 1 1.42 0.73 0.03
## ------------------------------------------------------------
## group: over 36
## vars n mean sd median trimmed mad min max range skew kurtosis se
## X1 1 54 0.25 0.29 0.15 0.2 0.11 0 1 1 1.24 0.18 0.04# also use histograms to examine your continuous variable
hist(d$npi)
# and cross_cases() to examine your categorical variables' cell count
cross_cases(d, over36)| #Total | |
|---|---|
| over36 | |
| 1 between 18 and 25 | 1964 |
| 2 between 26 and 35 | 114 |
| over 36 | 54 |
| #Total cases | 2132 |
# REMEMBER your test's level of power is determined by your SMALLEST subsample5 Check Your Assumptions
5.1 ANOVA Assumptions
- DV should be normally distributed across levels of the IV (we checked previously using “describeBy” function)
- All levels of the IVs should have equal number of cases and there should be no empty cells. Cells with low numbers decrease the power of the test (which increases chance of Type II error)
- Homogeneity of variance should be assured (using Levene’s Test)
- Outliers should be identified and removed – we will actually remove them this time!
- If you have confirmed everything above, the sampling distribution should be normal.
5.1.1 Check levels of IVs
# One-Way
table(d$over36)##
## 1 between 18 and 25 2 between 26 and 35 over 36
## 1964 114 54# our small number of participants owning rabbits is going to hurt us for the two-way anova, but it should be okay for the one-way anova
# so we'll create a new dataframe for the two-way analysis and call it d_tw5.1.2 Check homogeneity of variance
# use the leveneTest() command from the car package to test homogeneity of variance
# uses the 'formula' setup: formula is y~x1*x2, where y is our DV and x1 is our first IV and x2 is our second IV
# One-Way
leveneTest(npi~over36, data = d)## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 2 2.976 0.05121 .
## 2129
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 15.1.3 Check for outliers using Cook’s distance and Residuals VS Leverage plot
5.1.3.1 Run a Regression to get these outlier plots
# use this commented out section below ONLY IF if you need to remove outliers
# to drop a single outlier, use this code:
d <- subset(d, row_id!=c(1108))
# to drop multiple outliers, use this code:
d <- subset(d, row_id!=c(774) & row_id!=c(794))
# use the lm() command to run the regression
# formula is y~x1*x2 + c, where y is our DV, x1 is our first IV, x2 is our second IV.
reg_model <- lm(npi ~ over36, data = d) #for One-Way5.1.3.2 Check for outliers (One-Way)
# Cook's distance
plot(reg_model, 4)
# Residuals VS Leverage
plot(reg_model, 5)
5.1.3.3 Check for outliers (Two-Way)
5.2 Issues with My Data
The DV was not normally distributed across the IV
All levels of the IV are not equal, there are significantly more participants between the age of 18 and 25 than the other age groups.
Levene’s test was significant. We are ignoring this and continuing with the analysis anyway for this class.
We identified and removed 2 outliers.
[UPDATE this section in your HW.]
6 Run an ANOVA
# One-Way
aov_model <- aov_ez(data = d,
id = "row_id",
between = c("over36"),
dv = "npi",
anova_table = list(es = "pes"))## Contrasts set to contr.sum for the following variables: over367 View Output
nice(aov_model)## Anova Table (Type 3 tests)
##
## Response: npi
## Effect df MSE F pes p.value
## 1 over36 2, 2126 0.09 1.56 .001 .209
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1ANOVA Effect Size cutoffs from Cohen (1988): * η2 < 0.01 indicates a trivial effect * η2 >= 0.01 indicates a small effect * η2 >= 0.06 indicates a medium effect * η2 >= 0.14 indicates a large effect
8 Visualize Results
# One-Way
afex_plot(aov_model, x = "over36")
# NOTE: for the Two-Way, you will need to decide which plot version makes the most sense based on your data / rationale when you make the nice Figure 2 at the end9 Run Posthoc Tests (One-Way)
Only run posthocs IF the ANOVA test is significant! E.g., only run the posthoc tests on pet type if there is a main effect for pet type
emmeans(aov_model, specs="over36", adjust="tukey")## Note: adjust = "tukey" was changed to "sidak"
## because "tukey" is only appropriate for one set of pairwise comparisons## over36 emmean SE df lower.CL upper.CL
## 1 between 18 and 25 0.274 0.00682 2126 0.258 0.290
## 2 between 26 and 35 0.238 0.02830 2126 0.170 0.305
## over 36 0.219 0.04190 2126 0.119 0.319
##
## Confidence level used: 0.95
## Conf-level adjustment: sidak method for 3 estimatespairs(emmeans(aov_model, specs="over36", adjust="tukey"))## contrast estimate SE df t.ratio p.value
## 1 between 18 and 25 - 2 between 26 and 35 0.0364 0.0291 2126 1.252 0.4228
## 1 between 18 and 25 - over 36 0.0550 0.0424 2126 1.296 0.3974
## 2 between 26 and 35 - over 36 0.0186 0.0506 2126 0.368 0.9282
##
## P value adjustment: tukey method for comparing a family of 3 estimates10 Run Posthoc Tests (Two-Way)
Only run posthocs IF the ANOVA test is significant! E.g., only run the posthoc tests on pet type if there is a main effect for pet type.
11 Write Up Results
11.1 One-Way ANOVA
To test our hypothesis that there would be a significant effect of type of age on narcissitic personality inventory, we used a one-way ANOVA. Our data was unbalanced, with many more participants age 18-25 (n = 1964) than ages 26-35 (n = 114), and over 36 (n = 54). This significantly reduces the power of our test and increases the chances of a Type II error. We had 2 outliers decided to remove as we thought they might alter the significance of the ANOVA test. Our Levene’s test was significant (p = .05) which indicates that our data violates the assumption of homogeneity of variance. This suggests that there is an increased chance of Type I error. We continued with our analysis for the purpose of this class.
We did not find a significant effect of gender, F(2, 2129) = 1.57, p = .209, ηp2 = .001 (trivial effect size; Cohen, 1988). Therefore we did not conduct a Posthoc tests using Sidak’s adjustment because our results were not statistically significant
11.2 Two-Way ANOVA
References
Cohen J. (1988). Statistical Power Analysis for the Behavioral Sciences. New York, NY: Routledge Academic.